爬取"最好大学网站"大学排名

上半年在学bs4时的一个爬虫,主要是针对table标签的,可用于爬取其他类似网站,代码比较好更改

# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
import bs4

def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

def fillUnivList(ulist, html):
    soup = BeautifulSoup(html, "html.parser")
    #soup.find('tbody').children是列表迭代类型,而如果是soup.find('tbody')则是标签
    for tr in soup.find('tbody').children:
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[3].string])
            print(ulist)

def printUnivList(ulist, num):    
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    print(tplt.format("排名","学校名称","总分",chr(12288)))
    for i in range(num):
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))

def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20) # 20 univs
main()